Implementation and Comparison of Machine Learning Algorithms for Recognition of Fingerspelling in Indian Sign Language
Journal Title: Transactions on Machine Learning and Artificial Intelligence - Year 2017, Vol 5, Issue 5
Abstract
Communication is the biggest hurdle faced by the hearing and speech impaired in leading a normal life. In this context, Sign Language is the most prominent means of communication. Machine learning and Computer Vision is an integral part of today’s computing world. This research paper proposes a Machine Learning based system to recognize fingerspelling gestures present in Indian Sign Language. Edge Frequency technique is chosen for Feature Extraction. The system was implemented using Aforge.NET framework. A comparative analysis of the Machine Learning Algorithms consisting of Support Vector Machine (SVM), K- Nearest Neighbor (KNN), Adaptive Naïve Bayes Classifier (ANBC), Decision Tree (DT) and Random Forests (RF) is performed to find out which algorithm is the most suitable to recognize ISL. Comparison is done based on validation accuracies and confusion matrices obtained. The accuracy for KNN was found to be 97.44% while SVM and ANBC have an accuracy of 96.15% and 82.05% respectively.
Authors and Affiliations
Nikhil Aatrei M, Shreyas H N, Sumesh S. Iyer, Gowranga K H, R Bhakthavathsalam
Stock Recommendations using Bio-Inspired Computations on Social Media
The tremendous growth of the social networks has paved way for social interactions of investing communities about a company�s stock performance. Investors are able to share their comments on stocks using social media pla...
Research on Linear Fractional Town Traffic Flow Model Tactic
Traffic flow is a worldwide problem. It has many influencing factors and it is the complex system. Fractional calculus is a powerful tool for dealing with complex systems. Fractional calculus is a direct way of extending...
SIMARECH 3: A New Application for the Governance of Scientific Research
In the international context of research assessment, many countries appear to move critically towards a quantitative evaluation policy, which would eventually complement or replace the traditional peer review system. How...
An Efficient Brain Tumour Extraction in MR Images using Ford-Fulkerson Algorithm
Brain tumor division intends to discrete the diverse tumor tissues, for example, dynamic cells, necrotic core,and edema from typical cerebrum tissues of White Matter (WM), Gray Matter (GM), and Cerebrospinal Fluid (CSF)....
Inference-Based user’s Recommendation in E-Learning Systems
This paper proposes a technique of user’s recommendation for Elearning systems, which makes it possible to identify the best qualified profiles in a given field, the method is based on artificial intelligence in order to...